The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's primary purpose is to instruct an AI agent on how to execute the tigris CLI tool. This allows the agent to create, configure, and delete cloud storage buckets, snapshots, and forks. While this is the intended functionality, it grants the agent significant control over infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by processing external data and interpolating it into command-line arguments.
Ingestion points: The skill accepts untrusted inputs for bucket names, folder paths, webhook URLs, and SQL-like filters (e.g., in tigris buckets set-notifications).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within user-provided data are present in SKILL.md.
Capability inventory: The skill utilizes the tigris CLI tool to perform network operations (migrations, webhooks), configuration changes (CORS, TTL), and resource deletion.
Sanitization: There is no evidence of input validation or sanitization within the skill instructions to prevent command injection or malicious data processing.

tigris-buckets